SurfSplat: Conquering Feedforward 2D Gaussian Splatting with Surface Continuity Priors

TL;DR

SurfSplat introduces a novel feedforward 3D reconstruction method using 2D Gaussian Splatting with surface continuity priors, achieving higher geometric accuracy and more coherent surfaces than previous approaches.

Contribution

The paper proposes SurfSplat, a new framework that enhances 3D scene reconstruction by incorporating surface continuity priors and a high-resolution evaluation metric, outperforming prior methods.

Findings

Outperforms prior methods on standard metrics.

Achieves higher geometric and textural fidelity.

Demonstrates robustness across multiple datasets.

Abstract

Reconstructing 3D scenes from sparse images remains a challenging task due to the difficulty of recovering accurate geometry and texture without optimization. Recent approaches leverage generalizable models to generate 3D scenes using 3D Gaussian Splatting (3DGS) primitive. However, they often fail to produce continuous surfaces and instead yield discrete, color-biased point clouds that appear plausible at normal resolution but reveal severe artifacts under close-up views. To address this issue, we present SurfSplat, a feedforward framework based on 2D Gaussian Splatting (2DGS) primitive, which provides stronger anisotropy and higher geometric precision. By incorporating a surface continuity prior and a forced alpha blending strategy, SurfSplat reconstructs coherent geometry together with faithful textures. Furthermore, we introduce High-Resolution Rendering Consistency (HRRC), a new evaluation metric designed to evaluate high-resolution reconstruction quality. Extensive experiments on RealEstate10K, DL3DV, and ScanNet demonstrate that SurfSplat consistently outperforms prior methods on both standard metrics and HRRC, establishing a robust solution for high-fidelity 3D reconstruction from sparse inputs. Project page: https://hebing-sjtu.github.io/SurfSplat-website/